Renjie Liao

124 posts

Renjie Liao

Renjie Liao

@lrjconan

Fullmetal Alchemist of Deep Learning

Vancouver, British Columbia Katılım Mayıs 2011
694 Takip Edilen1.6K Takipçiler
Sabitlenmiş Tweet
Renjie Liao
Renjie Liao@lrjconan·
We show that Gaussian RBMs can generate good images just like other generative models, despite the single-layer architecture. Key innovations: 1) Gibbs-Langevin sampling; 2) modified Contrastive Divergence. Paper: arxiv.org/abs/2210.10318 Code: github.com/lrjconan/GRBM 1/2
GIF
English
9
107
529
0
Renjie Liao retweetledi
Jason Lee
Jason Lee@jasondeanlee·
A Chinese-American hero that inspired my parents' generation to study and stay in America.
Tsinghua University@Tsinghua_Uni

Prof. Chen Ning Yang, a world-renowned physicist, Nobel Laureate in Physics, Academician of the Chinese Academy of Sciences, Professor at Tsinghua University, and Honorary Director of the Institute for Advanced Study at Tsinghua University, passed away in Beijing due to illness at the age of 103. His life stands as a timeless chapter in human history—one that shines not only for China but for the global community of thinkers and innovators. His legacy will live on forever.

English
2
10
206
24.5K
Joey Bose
Joey Bose@bose_joey·
🎉Personal update: I'm thrilled to announce that I'm joining Imperial College London @imperialcollege as an Assistant Professor of Computing @ICComputing starting January 2026. My future lab and I will continue to work on building better Generative Models 🤖, the hardest AI4Science applications in computational biology 🧬and chemistry 🧪, and also a sprinkling of Deep Learning theory 📚 that supports these goals.
English
98
33
632
64K
Renjie Liao retweetledi
Felix (Yuxiang) Fu
Felix (Yuxiang) Fu@felix_yuxiang·
Interested in how to generate realistic human trajectories using diffusion with just one step🤔? This is now possible with MoFlow, a one-step Flow Matching method accompanied with Implicit Maximum Likelihood Estimation based distillation. 🚀 Join us at #CVPR2025 in Nashville!
English
1
3
6
1K
Renjie Liao
Renjie Liao@lrjconan·
🚀Our new work (RetroSynFlow) on retrosynthesis: 1) SOTA discrete flow matching that leverages synthons: products->synthons->reactants 2) effective test-time reward steering Led by my amazing students @RobinY798, @qi_yan98, with stellar collaborators Guy Wolf & @bose_joey
Robin Yadav@RobinY798

Excited to announce RetroSynFlow, a discrete flow matching framework for diverse and accurate retrosynthesis! 📄Paper available here: arxiv.org/abs/2506.04439 Joint work w/ @qi_yan98 , Guy Wolf, @bose_joey and @lrjconan . 👇 A quick overview 🧵

English
0
4
11
1.3K
Renjie Liao
Renjie Liao@lrjconan·
7/ More results on sorting and TSPs.
Renjie Liao tweet media
English
1
0
0
209
Renjie Liao
Renjie Liao@lrjconan·
Ever wondered how card shuffling can help solve combinatorial problems like sorting, jigsaw puzzles, or TSPs? Our ICLR 2025 (Oral) paper SymmetricDiffusers introduces a novel discrete diffusion model on finite symmetric groups to solve them in a unified and principled way!
Renjie Liao tweet media
English
2
3
19
1.1K
Renjie Liao
Renjie Liao@lrjconan·
Interested in LLMs for math reasoning? Check out our new work that builds 647K Math QA pairs and A Live Math Benchmark that is kept up-to-date, led by my brilliant students @sadegh_mahdavi4 @LiJonassen and Kaiwen!
Muchen Li@LiJonassen

🚀 Training an LLM for math reasoning, but high-quality data is scarce and costly? Check out our paper: “Leveraging Online Olympiad-Level Math Problems for LLM Training & Contamination-Resistant Evaluation.” 📖✨ TL;DR: 🔹 LLM-powered pipeline for scalable, high-quality data collection 🤖 🔹 647K Math QA pairs 📊 🔹 A Live Math Benchmark that is kept up-to-date⏳ Paper: arxiv.org/abs/2501.14275 Code & Data: github.com/DSL-Lab/aops Project Website: livemathbench.github.io Evaluation Leaderboard: livemathbench.github.io/leaderboard.ht… @askalphaxiv (for QA): alphaxiv.org/abs/2501.14275

English
0
0
5
354
Renjie Liao
Renjie Liao@lrjconan·
It means a lot to someone who has worked on Hopfield networks and Boltzmann machines. John and Geoff's foundational work has inspired generations of scientists, and it will keep doing so! I now have a compelling reason to keep teaching and researching these models! Huge Congrats!
The Nobel Prize@NobelPrize

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

English
0
0
26
1.6K
Renjie Liao
Renjie Liao@lrjconan·
Welcome to submit your work to NeurIPS 2024 workshop on Adaptive Foundation Models! Deadline: Oct. 4 AOE adaptive-foundation-models.org
Paul Vicol@PaulVicol

⌛️We extended the submission deadline for the NeurIPS 2024 Workshop on Adaptive Foundation Models to October 4 AoE! 🏁Submission site: #tab-your-consoles" target="_blank" rel="nofollow noopener">openreview.net/group?id=NeurI… 🌐Website: adaptive-foundation-models.org Organizers: @mengyer, @PaulVicol, @NailaMurray, @lrjconan, @BeidiChen, @weichiuma

English
0
0
6
1.1K
Yani Ioannou
Yani Ioannou@yanii·
I’m happy to share that I’ve been awarded a Schulich Research Chair by the Schulich School of Engineering at the University of Calgary! The Schulich Research Chair program is designed to recognize scholars with high accomplishments in research leadership and training.
English
10
2
29
4K

Keşfet

@bose_joey @imperialcollege @ICComputing @RobinY798 @qi_yan98 @VectorInst @ydlin718 @ECEUBC